Vehicle path planning by using adaptive constrained distance transformation

Abstract The adaptive constrained distance transformation (ACDT) is proposed to solve the vehicle path planning problem. The ACDT is a generalization of the constrained distance transformation. The incremental distance of the constrained distance transformation is modified into the incremental cost. By defining the incremental cost according to the incremental distance, the vehicle characteristics, and the local spatial properties of the terrain, the adaptive constrained distance transformation can be applied to solve the vehicle path planning problem that accounts for more than the Euclidean distance and hard constraints.

[1]  David Malah,et al.  Skeleton-based morphological coding of binary images , 1998, IEEE Trans. Image Process..

[2]  Thomas S. Huang,et al.  Image processing , 1971 .

[3]  Gábor Székely,et al.  Estimating shortest paths and minimal distances on digitized three-dimensional surfaces , 1993, Pattern Recognit..

[4]  Carlo Arcelli,et al.  Sketching a grey-tone pattern from its distance transform , 1996, Pattern Recognit..

[5]  Jim Piper,et al.  Computing distance transformations in convex and non-convex domains , 1987, Pattern Recognit..

[6]  G. Borgefors.  Distance transformations in arbitrary dimensions , 1984 .

[7]  Soo-Chang Pei,et al.  Finding the optimal driving path of a car using the modified constrained distance transformation , 1998, IEEE Trans. Robotics Autom..

[8]  Dinesh K. Pai,et al.  Multiresolution rough terrain motion planning , 1995, Proceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots.

[9]  Gunilla Borgefors,et al.  Distance transformations in digital images , 1986, Comput. Vis. Graph. Image Process..

[10]  Geoff A. W. West,et al.  Salience Distance Transforms , 1995, CVGIP Graph. Model. Image Process..

[11]  Frank Y. Shih,et al.  Size-invariant four-scan Euclidean distance transformation , 1998, Pattern Recognit..